File size: 3,533 Bytes
b49af5c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 |
import os
import sys
import gym
import random
import utils
import numpy as np
from collections import deque
from keras.layers import Dense
from keras.optimizers import Adam
from keras.models import Sequential
from matplotlib import pyplot as plt
class DQNAgent:
def __init__(self, state_size, action_size):
self.state_size = state_size
self.action_size = action_size
self.discount_factor = 0.99
self.learning_rate = 0.001
self.epsilon = 1.0
self.epsilon_decay = 0.999
self.epsilon_min = 0.01
self.batch_size = 64
self.train_start = 1000
self.memory = deque(maxlen=2000)
self.model = self.build_model()
self.target_model = self.build_model()
self.update_target_model()
def build_model(self):
model = Sequential()
model.add(Dense(24, input_dim=self.state_size, activation='relu',
kernel_initializer='he_uniform'))
model.add(Dense(24, activation='relu',
kernel_initializer='he_uniform'))
model.add(Dense(self.action_size, activation='linear',
kernel_initializer='he_uniform'))
model.compile(loss='mse', optimizer=Adam(lr=self.learning_rate))
return model
def update_target_model(self):
self.target_model.set_weights(self.model.get_weights())
def get_action(self, state):
if np.random.rand() <= self.epsilon:
return random.randrange(self.action_size)
else:
q_value = self.model.predict(state)
return np.argmax(q_value[0])
def append_sample(self, state, action, reward, next_state, done):
self.memory.append((state, action, reward, next_state, done))
if self.epsilon > self.epsilon_min:
self.epsilon *= self.epsilon_decay
def train_model(self):
if len(self.memory) < self.train_start:
return
batch_size = min(self.batch_size, len(self.memory))
mini_batch = random.sample(self.memory, batch_size)
update_input = np.zeros((batch_size, self.state_size))
update_target = np.zeros((batch_size, self.state_size))
action, reward, done = [], [], []
for i in range(self.batch_size):
update_input[i] = mini_batch[i][0]
action.append(mini_batch[i][1])
reward.append(mini_batch[i][2])
update_target[i] = mini_batch[i][3]
done.append(mini_batch[i][4])
target = self.model.predict(update_input)
target_val = self.target_model.predict(update_target)
for i in range(self.batch_size):
if done[i]:
target[i][action[i]] = reward[i]
else:
target[i][action[i]] = reward[i] + self.discount_factor * (
np.amax(target_val[i]))
self.model.fit(update_input, target, batch_size=self.batch_size,
epochs=1, verbose=0)
def run_DQN():
episodes = 500
seed = 1
results = []
game = 'CartPole-v0'
env = gym.make(game)
state_size = env.observation_space.shape[0]
action_size = env.action_space.n
agent = DQNAgent(state_size, action_size)
for e in range(episodes):
done = False
score = 0
state = env.reset()
state = np.reshape(state, [1, state_size])
while not done:
action = agent.get_action(state)
next_state, reward, done, info = env.step(action)
next_state = np.reshape(next_state, [1, state_size])
agent.append_sample(state, action, reward, next_state, done)
agent.train_model()
score += reward
state = next_state
if done:
agent.update_target_model()
results.append(score)
utils.save_trained_model(game, seed, 'DQN', agent.model)
plt.plot(results)
plt.show()
run_DQN()
|